DrBERT-4096 / tokenizer_config.json
abazoge's picture
Update tokenizer_config.json
768c976 verified
raw
history blame contribute delete
553 Bytes
{
"additional_special_tokens": [
"<s>NOTUSED",
"</s>NOTUSED"
],
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"max_len": 512,
"model_max_length": 4096,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "./special_tokens_map.json",
"tokenizer_class": "CamembertTokenizer",
"unk_token": "<unk>"
}